Publications by Guido Borghi

For decades, researchers of different areas, ranging from artificial intelligence to computer vision, have intensively investigated human-centered data, i.e., data in which the human plays a significant role, acquired through a non-invasive approach, such as cameras. This interest has been largely supported by the highly informative nature of this kind of data, which provides a variety of information with which it is possible to understand many aspects including, for instance, the human body or the outward appearance. Some of the main tasks related to human analysis are focused on the body (e.g., human pose estimation and anthropocentric measurement estimation), the hands (e.g., gesture detection and recognition), the head (e.g., head pose estimation), or the face (e.g., emotion and expression recognition). Additional tasks are based on non-corporal elements, such as motion (e.g., action recognition and human behavior understanding) and clothes (e.g., garment-based virtual try-on and attribute recognition). Unfortunately, privacy issues severely limit the usage and the diffusion of this kind of data, making the exploitation of learning approaches challenging. In particular, privacy issues behind the acquisition and the use of human-centered data must be addressed by public and private institutions and companies. Thirteen high-quality papers have been published in this Special Issue and are summarized in the following: four of them are focused on the human face (facial geometry, facial landmark detection, and emotion recognition), two on eye image analysis (eye status classification and 3D gaze estimation), five on the body (pose estimation, conversational gesture analysis, and action recognition), and two on the outward appearance (transferring clothing styles and fashion-oriented image captioning). These numbers confirm the high interest in human-centered data and, in particular, the variety of real-world applications that it is possible to develop.

In recent years, Human Pose Estimation has achieved impressive results on RGB images. The advent of deep learning architectures and large annotated datasets have contributed to these achievements. However, little has been done towards estimating the human pose using depth maps, and especially towards obtaining a precise 3D body joint localization. To fill this gap, this paper presents RefiNet, a depth-based 3D human pose refinement framework. Given a depth map and an initial coarse 2D human pose, RefiNet regresses a fine 3D pose. The framework is composed of three modules, based on different data representations, i.e. 2D depth patches, 3D human skeletons, and point clouds. An extensive experimental evaluation is carried out to investigate the impact of the model hyper-parameters and to compare RefiNet with off-the-shelf 2D methods and literature approaches. Results confirm the effectiveness of the proposed framework and its limited computational requirements.

Scenarios in which restrictions in data transfer and storage limit the possibility to compose a single dataset – also exploiting different data sources – to perform a batch-based training procedure, make the development of robust models particularly challenging. We hypothesize that the recent Continual Learning (CL) paradigm may represent an effective solution to enable incremental training, even through multiple sites. Indeed, a basic assumption of CL is that once a model has been trained, old data can no longer be used in successive training iterations and in principle can be deleted. Therefore, in this paper, we investigate the performance of different Continual Learning methods in this scenario, simulating a learning model that is updated every time a new chunk of data, even of variable size, is available. Experimental results reveal that a particular CL method, namely Learning without Forgetting (LwF), is one of the best-performing algorithms. Then, we investigate its usage and parametrization in Morphing Attack Detection and Object Classification tasks, specifically with respect to the amount of new training data that became available.

La presente invenzione riguarda un metodo per stimare automaticamente una posizione conforme della pupilla di un paziente durante l’esecuzione di un esame oftalmico. Il metodo si basa sull’acquisizione di immagini rappresentative della pupilla e sulla loro elaborazione mediante algoritmi di classificazione, comprendenti tecniche di machine learning, al fine di determinare la posizione della pupilla rispetto all’asse ottico di un dispositivo oftalmico o di valutare un parametro di stato della pupilla. L’invenzione riguarda inoltre un dispositivo per esami oftalmici che implementa tale metodo, comprendente un modulo ottico che include uno specchio dicroico configurato per deviare un segnale luminoso rappresentativo della pupilla verso un sensore ottico di acquisizione di immagini, consentendo al contempo ad un ulteriore segnale luminoso rappresentativo della pupilla di propagarsi senza interferenze rilevanti verso componenti ottiche interne del dispositivo oftalmico per l’esecuzione dell’esame di interesse. L’invenzione comprende altresì un kit elettronico collegabile ad un dispositivo oftalmico esistente, che ne consente l’aggiornamento funzionale per l’esecuzione della stima della posizione della pupilla senza alterare le funzionalità diagnostiche originarie. La soluzione proposta migliora l’affidabilità, la ripetibilità e l’usabilità degli esami oftalmici eseguiti da personale specializzato, mantenendo la compatibilità con la strumentazione oftalmica esistente.

Morphing Attack, i.e. the elusion of face verification systems through a facial morphing operation between a criminal and an accomplice, has recently emerged as a serious security threat. Despite the importance of this kind of attack, the development and comparison of Morphing Attack Detection (MAD) methods is still a challenging task, especially with deep learning approaches. Specifically, the lack of public datasets, the absence of common training and validation protocols, and the limited release of public source code hamper the reproducibility and objective comparison of new MAD systems. Usually, these aspects are mainly due to privacy concerns, that limit data transfers and storage, and to the recent introduction of the MAD task. Therefore, in this paper, we propose and publicly release Revelio, a modular framework for the reproducible development and evaluation of MAD systems. We include an overview of the modules, and describe the plugin system providing the possibility of extending native components with new functionalities. An extensive cross-datasets experimental evaluation is conducted to validate the framework and the performance of trained models on several publicly-released datasets, and to deeply analyze the main challenges in the MAD task based on single input images. We also propose a new metric, namely WAED, to summarize in a single value the error-based metrics commonly used in the MAD task, computed over different datasets, thus facilitating the comparative evaluation of different approaches. Finally, by exploiting Revelio, a new state-of-the-art MAD model (on SOTAMD single-image benchmark) is proposed and released.

: The accuracy and the overall performances of ophthalmic instrumentation, where specific analysis of eye images is involved, can be negatively influenced by invalid or incorrect frames acquired during everyday measurements of unaware or non-collaborative human patients and non-technical operators. Therefore, in this paper, we investigate and compare the adoption of several vision-based classification algorithms belonging to different fields, i.e., Machine Learning, Deep Learning, and Expert Systems, in order to improve the performance of an ophthalmic instrument designed for the Pupillary Light Reflex measurement. To test the implemented solutions, we collected and publicly released PopEYE as one of the first datasets consisting of 15 k eye images belonging to 22 different subjects acquired through the aforementioned specialized ophthalmic device. Finally, we discuss the experimental results in terms of classification accuracy of the eye status, as well as computational load analysis, since the proposed solution is designed to be implemented in embedded boards, which have limited hardware resources in computational power and memory size.

Y Existing Continual Learning benchmarks only partially address the complexity of real-life applications, limiting the realism of learning agents. In this letter, we propose and focus on benchmarks characterized by common key elements of real-life scenarios, including temporally ordered streams as input data, strong correlation of samples in short time ranges, high data distribution drift over the long time frame, and heavy class unbalancing. Moreover, we enforce online training constraints such as the need for frequent model updates without the possibility of storing a large amount of past data or passing the dataset multiple times through the model. Besides, we introduce a novel hybrid approach based on Continual Learning, whose architectural elements and replay memory management proved to be useful and effective in the considered scenarios. The experimental validation carried out, including comparisons with existing methods and an ablation study, confirms the validity and the suitability of the proposed approach.

Knowing the exact 3D location of workers and robots in a collaborative environment enables several real applications, such as the detection of unsafe situations or the study of mutual interactions for statistical and social purposes. In this paper, we propose a non-invasive and light-invariant framework based on depth devices and deep neural networks to estimate the 3D pose of robots from an external camera. The method can be applied to any robot without requiring hardware access to the internal states. We introduce a novel representation of the predicted pose, namely Semi-Perspective Decoupled Heatmaps (SPDH), to accurately compute 3D joint locations in world coordinates adapting efficient deep networks designed for the 2D Human Pose Estimation. The proposed approach, which takes as input a depth representation based on XYZ coordinates, can be trained on synthetic depth data and applied to real-world settings without the need for domain adaptation techniques. To this end, we present the SimBa dataset, based on both synthetic and real depth images, and use it for the experimental evaluation. Results show that the proposed approach, made of a specific depth map representation and the SPDH, overcomes the current state of the art.